mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-22 12:26:37 +00:00
f17ea7f146
* fix(heal): gate auto replacement formatting Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): require replacement target outcomes Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): bind resumes to replacement targets Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): fence healing marker ownership Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): cover replacement target completion Co-Authored-By: heihutu <heihutu@gmail.com> * docs(heal): clarify replacement recovery status Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): canonicalize replacement target checks Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): satisfy marker test module lint Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): scope automatic replacement format Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): require a mounted replacement target Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): avoid cloned ref slice in test Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): revalidate replacement before scanning Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): reset stale resume checkpoints Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): release scanner disk map before probing Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): persist replacement intent before format Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): fail closed on mountinfo read errors Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): fence replacement target identity Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): order replacement completion cleanup Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): atomically seal replacement completion Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): census replacement target shards Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): fence replacement recovery ownership Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): preserve replacement recovery anchors Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): satisfy replacement recovery lint gates Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): bind replacement identity to mount lease Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): cover durable replacement recovery states Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): validate persisted resume task identifiers Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): avoid blocking replacement marker CAS Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): report failed marker rollback Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): pin replacement resume schema compatibility Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): preserve durable recovery anchors Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): preserve public disk path semantics Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): use canonical replacement task ids Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): cover automatic replacement in 3x4 cluster Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): verify replacement target commits Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): persist replacement completion proof Co-Authored-By: heihutu <heihutu@gmail.com> * feat(heal): expose durable replacement status Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): bound durable replacement discovery Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): remove replacement readiness bypass Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): retry terminal replacement cleanup Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): isolate replacement intents from legacy resume Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): migrate legacy replacement intents at startup Co-Authored-By: heihutu <heihutu@gmail.com> * style(heal): apply strict clippy fix Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): prioritize active replacement recovery state Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): bind readiness to the admitted mount lease Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): atomically publish replacement intents Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): isolate replacement recovery directory Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): tolerate an empty recovery directory Co-Authored-By: heihutu <heihutu@gmail.com> * style(heal): remove redundant disk bytes conversion Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): reconcile proof-first replacement recovery Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): fence torn intent recovery Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): cover replacement migration conflicts Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): fence replacement lease mount identity Co-Authored-By: heihutu <heihutu@gmail.com> * test(heal): cover missing replacement path admission Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): reject conflicting legacy completion proof Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): fall back to proc mount identity Co-Authored-By: heihutu <heihutu@gmail.com> * feat(admin): expose replacement recovery status Surface the local durable replacement recovery snapshot in the background heal status response so operators can tell whether replacement cleanup is definitive or still pending. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): keep replacement status compatible Keep the existing background heal status response wire-compatible while retaining the Linux mount lease cleanup needed for the replacement recovery branch. Co-Authored-By: heihutu <heihutu@gmail.com> * style(ecstore): match linux mount lease formatting Keep Linux rustfmt output stable for the replacement mount lease comparison. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): qualify mount lease test constant Use the disk module path for the format config constant in the Linux mount lease regression test. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): keep procfd mount roots directory-safe Use a procfd path with an explicit directory component so Unix directory guards can open the replacement mount lease root with O_NOFOLLOW while preserving handle-relative I/O semantics. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): delete empty leased buckets via dirfd Use the held mount lease fd as the parent for non-force empty bucket deletion on Linux so procfd-rooted paths do not get rejected as BucketNotEmpty. Also make the download-part OpenOptions truncate behavior explicit and keep fsync test recording stable across procfd canonicalization. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): scan leased bucket paths for emptiness Use the local disk I/O root for bucket emptiness probes before non-force bucket deletion and table-bucket metadata checks. This keeps validation on the same mount instance as the subsequent local disk delete path. Co-Authored-By: heihutu <heihutu@gmail.com> * test(ecstore): align lease path test probes Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): block unsafe replacement recovery restarts Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): defer blocked replacement candidates Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): retry transient replacement discovery Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): keep transient recovery errors retryable Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): block corrupt legacy replacement state Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): classify flat replacement intent corruption Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): keep transient resume loads retryable Classify malformed legacy replacement state as blocking corruption while preserving disk and transient load failures for retry. This avoids permanently blocking replacement recovery on temporary storage errors. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): avoid latching transient legacy publishes Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): retry blocked legacy migrations Co-Authored-By: heihutu <heihutu@gmail.com> * fix(heal): defer blocked startup recoveries Co-Authored-By: heihutu <heihutu@gmail.com> * fix(ecstore): preserve disk sync limiter across lease roots Co-Authored-By: heihutu <heihutu@gmail.com> --------- Co-authored-by: heihutu <heihutu@gmail.com> Co-authored-by: zhi22915 <qiuzgang@gmail.com>
126 lines
4.2 KiB
Rust
126 lines
4.2 KiB
Rust
// Copyright 2024 RustFS Team
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
use crate::os::{DiskInfo, IOStats};
|
|
use rustix::fs::{StatVfs, statvfs};
|
|
use std::io::Error;
|
|
use std::path::Path;
|
|
|
|
/// Returns total and free bytes available in a directory, e.g. `/`.
|
|
pub fn get_info(p: impl AsRef<Path>) -> std::io::Result<DiskInfo> {
|
|
let path_display = p.as_ref().display();
|
|
let stat = statvfs(p.as_ref())?;
|
|
|
|
// According to POSIX statvfs definition:
|
|
// f_bsize: File system block size.
|
|
// f_frsize: Fundamental file system block size.
|
|
// f_blocks: Total number of blocks on file system in units of f_frsize.
|
|
//
|
|
// We should use f_frsize to calculate the size in bytes.
|
|
// If f_frsize is 0 (which shouldn't happen on compliant systems), fallback to f_bsize.
|
|
let bsize = if stat.f_frsize > 0 {
|
|
stat.f_frsize as u64
|
|
} else {
|
|
stat.f_bsize as u64
|
|
};
|
|
|
|
let bfree = stat.f_bfree as u64;
|
|
let bavail = stat.f_bavail as u64;
|
|
let blocks = stat.f_blocks as u64;
|
|
|
|
let reserved = match bfree.checked_sub(bavail) {
|
|
Some(reserved) => reserved,
|
|
None => {
|
|
return Err(Error::other(format!(
|
|
"detected f_bavail space ({bavail}) > f_bfree space ({bfree}), fs corruption at ({path_display}). please run 'fsck'",
|
|
)));
|
|
}
|
|
};
|
|
|
|
let total = match blocks.checked_sub(reserved) {
|
|
Some(total) => total * bsize,
|
|
None => {
|
|
return Err(Error::other(format!(
|
|
"detected reserved space ({reserved}) > blocks space ({blocks}), fs corruption at ({path_display}). please run 'fsck'",
|
|
)));
|
|
}
|
|
};
|
|
|
|
let free = bavail * bsize;
|
|
let used = match total.checked_sub(free) {
|
|
Some(used) => used,
|
|
None => {
|
|
return Err(Error::other(format!(
|
|
"detected free space ({free}) > total drive space ({total}), fs corruption at ({path_display}). please run 'fsck'"
|
|
)));
|
|
}
|
|
};
|
|
|
|
let st = rustix::fs::stat(p.as_ref())?;
|
|
|
|
Ok(DiskInfo {
|
|
total,
|
|
free,
|
|
used,
|
|
files: stat.f_files,
|
|
ffree: stat.f_ffree,
|
|
fstype: get_fs_type(&stat).to_string(),
|
|
major: rustix::fs::major(st.st_dev) as u64,
|
|
minor: rustix::fs::minor(st.st_dev) as u64,
|
|
..Default::default()
|
|
})
|
|
}
|
|
|
|
fn get_fs_type(_stat: &StatVfs) -> &'static str {
|
|
"UNKNOWN"
|
|
}
|
|
|
|
pub fn same_disk(disk1: &str, disk2: &str) -> std::io::Result<bool> {
|
|
let stat1 = rustix::fs::stat(disk1)?;
|
|
let stat2 = rustix::fs::stat(disk2)?;
|
|
|
|
Ok(stat1.st_dev == stat2.st_dev)
|
|
}
|
|
|
|
/// Return whether `path` is mounted separately from its parent directory.
|
|
///
|
|
/// This is intentionally conservative on non-Linux Unix platforms. Linux
|
|
/// uses mountinfo to recognize bind mounts; elsewhere a shared device number
|
|
/// cannot distinguish a bind mount from a normal directory safely.
|
|
pub fn is_mount_point(path: &Path) -> std::io::Result<bool> {
|
|
let metadata = std::fs::symlink_metadata(path)?;
|
|
if !metadata.file_type().is_dir() || metadata.file_type().is_symlink() {
|
|
return Ok(false);
|
|
}
|
|
let parent = path.parent().ok_or_else(|| Error::other("mount point has no parent"))?;
|
|
Ok(rustix::fs::stat(path)?.st_dev != rustix::fs::stat(parent)?.st_dev)
|
|
}
|
|
|
|
pub fn get_physical_device_ids(disk: &str) -> std::io::Result<Vec<String>> {
|
|
let stat = rustix::fs::stat(disk)?;
|
|
let major = rustix::fs::major(stat.st_dev);
|
|
let minor = rustix::fs::minor(stat.st_dev);
|
|
|
|
Ok(vec![format!("{major}:{minor}")])
|
|
}
|
|
|
|
pub fn check_cross_device_mounts(_paths: &[String]) -> std::io::Result<()> {
|
|
Ok(())
|
|
}
|
|
|
|
#[cfg(not(target_os = "linux"))]
|
|
pub fn get_drive_stats(_major: u32, _minor: u32) -> std::io::Result<IOStats> {
|
|
Ok(IOStats::default())
|
|
}
|